Design of an Artificial Vision System for Exercise Monitoring in Healthy Aging

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: Reyes, Karla Miriam, Zapata, Gloria, Heydari, Maryam, Villalba-Mora, Elena, Imbert, Ricardo
Format: Recurso digital
Language:English
Published: Zenodo 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902013883711488
author Reyes, Karla Miriam
Zapata, Gloria
Heydari, Maryam
Villalba-Mora, Elena
Imbert, Ricardo
author_facet Reyes, Karla Miriam
Zapata, Gloria
Heydari, Maryam
Villalba-Mora, Elena
Imbert, Ricardo
contents <p>This study presents the design and pilot evaluation of a computer vision–based system for monitoring exercise performance in older adults, aiming to reduce frailty-related risks without the need for wearable sensors. Using MediaPipe and OpenCV, the system tracks posture and movement in real time and provides feedback on exercise execution. A pilot test was conducted with 14 volunteers performing seven exercises from the Vivifrail Spanish program (Wheel A).</p> <p>Performance was evaluated using performance analysis, yielding recognition rates between 91.06% and 100% across exercises. While the system showed high accuracy in detecting posture and repetitions, challenges such as camera positioning, clothing variability, and the absence of validation in the target population remain. These findings demonstrate the feasibility of computer vision for exercise monitoring and support its potential as an accessible tool for fall prevention and functional assessment in older adults.</p> <p>Future work will focus on clinical validation and integration into mobile platforms for home-based use. This approach will allow the older population to perform the exercises from the Vivifrail program effectively, while professionals, such as physiotherapists and geriatricians, can monitor their progress remotely and adjust the program as needed.</p>
format Recurso digital
id zenodo_https___doi_org_10_4028_p-P2KnGL
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Design of an Artificial Vision System for Exercise Monitoring in Healthy Aging
Reyes, Karla Miriam
Zapata, Gloria
Heydari, Maryam
Villalba-Mora, Elena
Imbert, Ricardo
Biomechanics
Computer vision
Exercise Monitoring
Accidental Falls/prevention & control
Healthy Aging
<p>This study presents the design and pilot evaluation of a computer vision–based system for monitoring exercise performance in older adults, aiming to reduce frailty-related risks without the need for wearable sensors. Using MediaPipe and OpenCV, the system tracks posture and movement in real time and provides feedback on exercise execution. A pilot test was conducted with 14 volunteers performing seven exercises from the Vivifrail Spanish program (Wheel A).</p> <p>Performance was evaluated using performance analysis, yielding recognition rates between 91.06% and 100% across exercises. While the system showed high accuracy in detecting posture and repetitions, challenges such as camera positioning, clothing variability, and the absence of validation in the target population remain. These findings demonstrate the feasibility of computer vision for exercise monitoring and support its potential as an accessible tool for fall prevention and functional assessment in older adults.</p> <p>Future work will focus on clinical validation and integration into mobile platforms for home-based use. This approach will allow the older population to perform the exercises from the Vivifrail program effectively, while professionals, such as physiotherapists and geriatricians, can monitor their progress remotely and adjust the program as needed.</p>
title Design of an Artificial Vision System for Exercise Monitoring in Healthy Aging
topic Biomechanics
Computer vision
Exercise Monitoring
Accidental Falls/prevention & control
Healthy Aging
url https://doi.org/10.4028/p-P2KnGL